Python NLTK Sentiment Analysis with Text Classification Demo | Hacker News Reader

Python NLTK Sentiment Analysis with Text Classification Demo

text-processing.com

68 pointsllambda9 comments

Open articleView on HN

Worth mentioning:

Open source sentiment analysis library based on NLTK: http://github.com/tawlk/synt

(Trains on as much twitter data as you want to learn internet slang)

Simple gist to do basic sentiment analysis:

https://gist.github.com/1266556

I wrote an article on use the NLTK library for gender prediction http://stephenholiday.com/articles/2011/gender-prediction-wi...

It's quite a versatile library.

The NLTK python lib is a great tool. I've been playing around with this recently and having a lot of fun. More recently I started looking at SCOTUS oral transcripts:

http://jarv.org/2012/02/a-text-analysis-of-supreme-court-ora...

The two articles here by the same author are interesting for folks who are interested in more about sentiment analysis

http://streamhacker.com/2010/05/10/text-classification-senti... http://streamhacker.com/2010/06/16/text-classification-senti...

https://github.com/dotpot/Custom-String-Parser

Needs more cowbell. "Wasn't that a fucking great movie?" => 0.7 Negative sentiment.

At least it got this one correct. "Mr. Madison, what you've just said is one of the most insanely idiotic things I have ever heard. At no point in your rambling, incoherent response were you even close to anything that could be considered a rational thought. Everyone in this room is now dumber for having listened to it. I award you no points, and may God have mercy on your soul." 0.8 Negative Sentiment.

"A better film has never been made. If this film was any better, it would simply cease to exist. Really, nothing about it could be improved. I have no complaints whatsoever about the acting, the script, or the cinematography. I was sad to see it end. I am going to go back tomorrow and watch it again."

1.0 Negative sentiment

WOW! That is unbelievable. Usually things get better with more tokens. What a broken library.

"The movie was great"

Neg?

Reply on news.ycombinator.com